noise

I have googled a bit but was never able to find an answer. What should be my first approach to simulate a video and audio noise from TV on screen? I mean, when my TV antenna is removed but the TV is still on (like they show in Japanese horror movies sometimes). I can use ffmpeg or any other technique but what is the simplest possible form of the signal? Create video and audio noise, artifacts, and errors with ffmpeg Noise Using filters The geq (video "generic equation") filter (with nullsrc as its "blank canvas") can create video noise, and the aevalsrc filter can create white noise audio:

I want to use the wiimote to control a cursor WITHOUT the infrared sensor bar. I'm using the pitch and roll values for this. The problem is that when the pitch is close to 0 degrees, the roll is very unstable, and when the pitch is close to 90 degrees, it is itself very unstable, but the roll is fine. Im polling the wiimote very frequently, so im averaging the last 20 values for both pitch and roll, and I can get the cursor to go where I want. The only problem is that there is still alot of uncontrolable shaking. Any ideas on how I can reduce it? (Or even get a more precise position without

I have data from a sensor and I need to find the frequency of it. It looks like fft() seems to be the way to go, but the MATLAB docs only show how to get a graph of the frequencies, I don't know what to do from there. Here's what my data looks like: One way to go is indeed to use an fft. Since the fft gives you the frequency representation of the signal, you want to look for the maximum, and since the fft is a complex signal, you will want to take the absolute value first. The index will correspond to the normalized frequency with maximum energy. Last, if your signal has an offset, as is the

[EDIT] The answer by @Claudio gives me a really good tip on how to filter out outliers. I do want to start using a Kalman filter on my data though. So I changed the example data below so that it has subtle variation noise which are not so extreme (which I see a lot as well). If anybody else could give me some direction on how to use PyKalman on my data that would be great. [/EDIT] For a robotics project I'm trying to track a kite in the air with a camera. I'm programming in Python and I pasted some noisy location results below (every item also has a datetime object included, but I left them

I have a dataset of accelerometric data that is affected by electical spikes. I'm looking for a good method to filter out or reduce these spikes as need to calculate on these data a rolling window of FFT and other statistical indicators such as kurtosis and skewness. I can't simply delete these outliers or replace them with NaN. Sampling 2000[hz] Until now I've tried on MATLAB 2012b: Wavelet denoising (Haar wavelet) Median Filter Despike and iterpolate approach Can you suggest a proper approach to deal with these data? Download example dataset I would suggest some local smoothing. By defining